Model: GELU Model: 1 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1832 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.6286. Min Act: -0.1700

Data Index: 86322 (C4 (Web Text))

Max Activating Token Index: 694

Text #1

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.5935. Min Act: -0.1700

Data Index: 75718 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.5598. Min Act: -0.1700

Data Index: 314249 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.5354. Min Act: -0.1700

Data Index: 1415576 (Python Code)

Max Activating Token Index: 946

Text #4

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.5284. Min Act: -0.1700

Data Index: 1444450 (Python Code)

Max Activating Token Index: 373

Text #5

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.4810. Min Act: -0.1700

Data Index: 1608670 (Python Code)

Max Activating Token Index: 762

Text #6

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.4802. Min Act: -0.1700

Data Index: 1620346 (Python Code)

Max Activating Token Index: 268

Text #7

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.4898. Min Act: -0.1700

Data Index: 1272055 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.4258. Min Act: -0.1700

Data Index: 913583 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.4372. Min Act: -0.1699

Data Index: 1475617 (Python Code)

Max Activating Token Index: 296

Text #10

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.4523. Min Act: -0.1700

Data Index: 1084977 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.3994. Min Act: -0.1700

Data Index: 640123 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.4085. Min Act: -0.1678

Data Index: 786899 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.4151. Min Act: -0.1700

Data Index: 820640 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.4189. Min Act: -0.1700

Data Index: 696345 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.3951. Min Act: -0.1700

Data Index: 565630 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.3737. Min Act: -0.1700

Data Index: 1169453 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.3878. Min Act: -0.1684

Data Index: 1433596 (Python Code)

Max Activating Token Index: 625

Text #18

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.3683. Min Act: -0.1700

Data Index: 1379139 (Python Code)

Max Activating Token Index: 732

Text #19

Max Range: 3.6286. Min Range: -3.6286

Max Act: 3.3856. Min Act: -0.1700

Data Index: 1440617 (Python Code)

Max Activating Token Index: 440